Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.48
    alled
    0.45
    bacteria
    0.44
    uliar
    0.43
    orescence
    0.42
    beans
    0.42
    aled
    0.41
    ãy
    0.41
    iotics
    0.41
    áreas
    0.41
    POSITIVE LOGITS
     in
    0.56
    ↵
    0.54
     can
    0.54
    ת
    0.52
     party
    0.52
     on
    0.51
     as
    0.50
     team
    0.49
     for
    0.48
     had
    0.48
    Act Density 0.040%

    No Known Activations